机器人 / 具身智能 - arXivDaily 专题

2207.06269 2022-07-14 cs.LG 57%

Policy Optimization with Sparse Global Contrastive Explanations

Jiayu Yao, Sonali Parbhoo, Weiwei Pan, Finale Doshi-Velez

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

Comments Accepted at IMLH Workshop, ICML 2022

2207.05850 2022-07-14 math.OC cs.LG cs.SY eess.SY 57%

Compactly Restrictable Metric Policy Optimization Problems

Victor D. Dorobantu, Kamyar Azizzadenesheli, Yisong Yue

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments 11 pages, 1 figure, submitted to Transactions on Automatic Control

2207.03257 2022-07-08 cs.CE cs.LG 57%

Vessel-following model for inland waterways based on deep reinforcement learning

Fabian Hart, Ostap Okhrin, Martin Treiber

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

2207.03214 2022-07-08 cs.AI 57%

Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios

Francisco Cruz, Charlotte Young, Richard Dazeley, Peter Vamplew

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.AI

Comments 8 pages, 8 figures

2207.00636 2022-07-05 q-bio.NC cs.LG cs.NE 57%

Action-modulated midbrain dopamine activity arises from distributed control policies

Jack Lindsey, Ashok Litwin-Kumar

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

2207.00202 2022-07-04 cs.RO 57%

DiffPills: Differentiable Collision Detection for Capsules and Padded Polygons

Kevin Tracy, Taylor A. Howell, Zachary Manchester

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

2202.04849 2022-07-04 cs.LG 57%

SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition

Dylan Slack, Yinlam Chow, Bo Dai, Nevan Wichers

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

2108.12916 2022-06-28 cs.LG 57%

A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning

Tianchi Cai, Wenpeng Zhang, Lihong Gu, Xiaodong Zeng, Jinjie Gu

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

Comments Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning, 2021

1905.03231 2022-06-20 cs.LG stat.ML 57%

Smoothing Policies and Safe Policy Gradients

Matteo Papini, Matteo Pirotta, Marcello Restelli

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

2206.06090 2022-06-14 stat.ML cs.LG cs.NE 57%

Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control

Maximilian Hüttenrauch, Gerhard Neumann

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

Comments 26 pages, 15 figures

2202.01288 2022-06-14 cs.LG 57%

Imitation Learning by Estimating Expertise of Demonstrators

Mark Beliaev, Andy Shih, Stefano Ermon, Dorsa Sadigh, Ramtin Pedarsani

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments ICML 2022. 17 pages, 4 figures

2202.13252 2022-06-07 cs.AI 57%

The Quest for a Common Model of the Intelligent Decision Maker

Richard S. Sutton

专题命中模仿学习与强化学习：world model(abstract)；分类 cs.AI

Comments Will appear as an extended abstract at the fifth Multi-disciplinary Conference on Reinforcement Learning and Decision Making, held in Providence, Rhode Island, June 8-11, 2022

2205.15056 2022-05-31 q-fin.MF cs.LG q-fin.PM 57%

Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength

Huifang Huang, Ting Gao, Yi Gui, Jin Guo, Peng Zhang

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

2203.04735 2022-05-26 cs.GR cs.LG 57%

A Survey on Reinforcement Learning Methods in Character Animation

Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C. Karen Liu, Julien Pettré, Michiel van de Panne, Marie-Paule Cani

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

Comments 27 pages, 6 figures, Eurographics STAR, Computer Graphics Forum

2205.05061 2022-05-25 cs.LG 57%

On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer

Marco Pleines, Konstantin Ramthun, Yannik Wegener, Hendrik Meyer, Matthias Pallasch, Sebastian Prior, Jannik Drögemüller, Leon Büttinghaus, Thilo Röthemeyer, Alexander Kaschwig, Oliver Chmurzynski, Frederik Rohkrähmer, Roman Kalkreuth, Frank Zimmer, Mike Preuss

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

Comments Accepted at IEEE Conference on Games 2022, 8 pages, 6 figures, 3 tables

2205.08716 2022-05-19 cs.LG 57%

No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL

Han Wang, Archit Sakhadeo, Adam White, James Bell, Vincent Liu, Xutong Zhao, Puer Liu, Tadashi Kozuno, Alona Fyshe, Martha White

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

2204.13060 2022-05-18 cs.LG 57%

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair, Patrick Yin, Sergey Levine

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.LG

Comments ICML 2022. 20 Pages, 15 Figures, 4 Tables. Website at https://sites.google.com/view/gc-bisimulation

2205.05569 2022-05-12 cs.LG 57%

Delayed Reinforcement Learning by Imitation

Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

2205.03471 2022-05-10 cond-mat.soft cs.LG physics.comp-ph 57%

Dynamically writing coupled memories using a reinforcement learning agent, meeting physical bounds

Théo Jules, Laura Michel, Adèle Douin, Frédéric Lechenault

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.LG

Comments Main text: 5 pages, 4 figures. Submitted to PNAS

2109.03880 2022-05-05 eess.SY cs.RO cs.SY 57%

Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning

Brian Gaudet, Roberto Furfaro

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

Comments Preprint for 2023 Scitech GN&C submission

2110.14457 2022-05-03 cs.LG 57%

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier, Alessandro Lazaric, Ludovic Denoyer

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

Comments ICLR 2022

2110.07409 2022-05-02 math.OC cs.LG math.AG 57%

The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs

Johannes Müller, Guido Montúfar

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

Comments Camera ready version for ICLR 2022, 45 pages, 8 figures

Journal ref Proceedings of the 10th International Conference on Learning Representations (ICLR 2022)

2204.11475 2022-04-26 cs.RO 57%

Adaptive actuation of magnetic soft robots using deep reinforcement learning

Jianpeng Yao, Quanliang Cao, Yuwei Ju, Yuxuan Sun, Ruiqi Liu, Xiaotao Han, Liang Li

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

2105.12991 2022-04-25 cs.LG 57%

Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization

Taisuke Kobayashi

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments 14 pages, 6 figures

Journal ref Neural Networks, 2022

2112.08516 2022-04-13 cs.RO cs.SY eess.SY 57%

Safety-Aware Preference-Based Learning for Safety-Critical Control

Ryan K. Cosner, Maegan Tucker, Andrew J. Taylor, Kejun Li, Tamás G. Molnár, Wyatt Ubellacker, Anil Alan, Gábor Orosz, Yisong Yue, Aaron D. Ames

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

Comments 15 pages, 4 figures

2204.04823 2022-04-12 cs.RO 57%

ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments

Yash Shukla, Christopher Thierauf, Ramtin Hosseini, Gyan Tatiya, Jivko Sinapov

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.RO

2203.15290 2022-03-30 cs.RO 57%

Design strategies for controlling neuron-connected robots using reinforcement learning

Haruto Sawada, Naoki Wake, Kazuhiro Sasabuchi, Jun Takamatsu, Hirokazu Takahashi, Katsushi Ikeuchi

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

Comments Last updated March 29th, 2022

2203.14033 2022-03-29 cs.RO cs.SY eess.SY 57%

Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learning

Qiyu Sun, Jinbao Fang, Wei Xing Zheng, Yang Tang

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

2203.11842 2022-03-23 cs.LG 57%

X-MEN: Guaranteed XOR-Maximum Entropy Constrained Inverse Reinforcement Learning

Fan Ding, Yeiang Xue

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

2203.11369 2022-03-23 cs.LG 57%

Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL

Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

1. 模仿学习与强化学习 4134 篇

Policy Optimization with Sparse Global Contrastive Explanations

Compactly Restrictable Metric Policy Optimization Problems

Vessel-following model for inland waterways based on deep reinforcement learning

Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios

Action-modulated midbrain dopamine activity arises from distributed control policies

DiffPills: Differentiable Collision Detection for Capsules and Padded Polygons

SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition

A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning

Smoothing Policies and Safe Policy Gradients

Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control

Imitation Learning by Estimating Expertise of Demonstrators

The Quest for a Common Model of the Intelligent Decision Maker

Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength

A Survey on Reinforcement Learning Methods in Character Animation

On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer

No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Delayed Reinforcement Learning by Imitation

Dynamically writing coupled memories using a reinforcement learning agent, meeting physical bounds

Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs

Adaptive actuation of magnetic soft robots using deep reinforcement learning

Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization

Safety-Aware Preference-Based Learning for Safety-Critical Control

ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments

Design strategies for controlling neuron-connected robots using reinforcement learning

Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learning

X-MEN: Guaranteed XOR-Maximum Entropy Constrained Inverse Reinforcement Learning

Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL